AgentSkillsCN

root-cause-analysis

帮助用户从 Git 迁移至 Jujutsu(jj)。当用户提及 Git 迁移、Git 向 jj 的过渡、jj 环境下的 Git 命令,或希望从 Git 的视角理解 jj 时,可选用此技能。其中包含详尽的 Git 至 jj 命令翻译,以及两者的思维模式差异对比。

SKILL.md
--- frontmatter
name: root-cause-analysis
description: Analyze telemetry data for root cause analysis using Kopai CLI. Use when debugging errors, investigating latency issues, tracing request flows across services, or correlating logs with traces.
license: Apache-2.0
metadata:
  author: kopai
  version: "1.0.0"

Root Cause Analysis with Kopai

Guide for debugging production issues using telemetry data (traces, logs, metrics) via Kopai CLI.

Prerequisites

Ensure access to Kopai app backend. Make sure the services are set up to send their OpenTelemetry data to Kopai. See otel-instrumentation skill for setup.

RCA Workflow Summary

  1. Find error traces
  2. Get full trace context
  3. Correlate logs with trace
  4. Check related metrics
  5. Identify root cause

Rules

1. Workflow (CRITICAL)

  • workflow-find-errors - Find Error Traces
  • workflow-get-context - Get Full Trace Context
  • workflow-correlate-logs - Correlate Logs with Trace
  • workflow-check-metrics - Check Related Metrics

2. Patterns (HIGH)

  • pattern-http-errors - HTTP Error Debugging
  • pattern-slow-requests - Slow Request Analysis
  • pattern-distributed - Distributed Failure Tracing
  • pattern-log-driven - Log-Driven Investigation

Read rules/<rule-name>.md for details.

Tips

  1. Always use --json for programmatic analysis
  2. Pipe to jq for filtering/aggregation
  3. Start with errors, then trace backwards
  4. Check span Duration to find bottlenecks
  5. Correlate TraceId across traces, logs, metrics

References